© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1220
    Prev
    Next
    INDEX
    Explanations

    hospital and patients

    np_acts-logits-general · gemini-2.5-flash-lite

    mentions of hospitals, hospital rooms, and hospital settings.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The main thing this neuron does is identify explicit references to hospital settings or clinical procedures (e.g., mentions of “hospital,” “IV bag,” “policy,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gilet
    -1.00
     escrow
    -0.87
     backyard
    -0.85
     orgas
    -0.85
     Veterin
    -0.85
     /><
    -0.84
    烦恼
    -0.84
     Embal
    -0.82
     parf
    -0.82
     OneDrive
    -0.81
    POSITIVE LOGITS
     hospital
    2.39
     patients
    2.39
     nurses
    2.19
     patient
    2.11
     Patients
    1.76
     bedside
    1.75
     Hospital
    1.71
     nurse
    1.70
     Patient
    1.63
     discharge
    1.62
    Activations Density 0.064%

    No Known Activations